© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80277
    Prev
    Next
    INDEX
    Explanations

    testing concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    month vacation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     탄
    0.61
    ût
    0.47
     개념
    0.46
     식
    0.46
     새로운
    0.46
     어려운
    0.46
     품질
    0.46
     절
    0.46
     हळ
    0.45
     할인
    0.45
    POSITIVE LOGITS
    ia
    0.51
     imaged
    0.50
    王者
    0.49
     imagenes
    0.49
    Imagenes
    0.48
    入力
    0.47
    n
    0.47
     ASSERT
    0.46
    木
    0.46
    }'
    0.46
    Activations Density 0.000%

    No Known Activations